CVE Tools
Sign in

CVE-2026-47391

PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution

Published: Jul 21, 2026Updated: Jul 23, 2026 Sources: CVE List NVDCWE-95
9.8CRITICAL
NVD MITRE
EPSS Score
0.8%
Top 47.5%
CISA KEV
Not in KEV
Exploits
No Known Exploits
Remediation
No Fix Available
Self-Check
Not available

Description

PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a `calculate(expression)` tool implemented with Python `eval()`. The example also binds to `0.0.0.0`. A remote unauthenticated attacker can send `message/send` to `/a2a`; the request reaches `agent.chat()`, and a real LLM can invoke the registered `calculate` tool. In testing with `gemini/gemini-2.5-flash-lite`, this resulted in arbitrary Python execution in the server process, confirmed by creation of a marker file from an unauthenticated HTTP request. The issue affects deployments following the official A2A example or similar unauthenticated public A2A deployments with unsafe tools. The default unauthenticated A2A surface also exposes task history and task cancellation APIs, increasing confidentiality and integrity impact. Version 4.6.40 patches the issue.

No summary for this CVE yet.

CVSS Vector Breakdown

AV:NAC:LPR:NUI:NS:UC:HI:HA:H
Exploitability
AV:NAttack Vector
Network
AC:LAttack Complexity
Low
PR:NPrivileges Required
None
UI:NUser Interaction
None
Scope
S:UScope
Unchanged
Impact
C:HConfidentiality
High
I:HIntegrity
High
A:HAvailability
High
Open in CVSS calculator →

Weaknesses

CWE-95CWE-306

Affected Products

MervinPraison
commercialaka praisonai, praisonaiagents, featured image
PraisonAIMixed
AI / ML / ai-agent-tooling

Exploitability

No known exploits, KEV entries, or remediation guidance available for this vulnerability yet.
Is your org exposed to CVE-2026-47391?We can run the check for you — a free external exposure review, no install. Check my exposure

Attack Graph

Products CVE Techniques Tactics

Click technique nodes for MITRE ATT&CK details · drag to pan · Ctrl/⌘ + scroll to zoom, or go fullscreen.

MITRE ATT&CK

2 techniques
Initial Access
View detailed technique mapping

References

https://github.com/MervinPraison/PraisonAI/commit/e0fb8e7dd1ee6759c18ed07f436c21dbd9c20747
github.com
https://github.com/MervinPraison/PraisonAI/pull/1793
github.com
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg22-4gmj-prxw
github.com

Unlock Complete Vulnerability Intelligence

Get the full picture for CVE-2026-47391 and every CVE in our database. Create a free account — no credit card required.

Create Free Account
Plain-language analysis
Impact assessment and exploitation scenario in plain English
Attack graph visualization
Interactive attack path and kill chain mapping
Exploit details & PoC links
ExploitDB, Metasploit, GitHub PoCs with direct links
Nuclei scanner templates
Ready-to-use vulnerability scanner templates
Full remediation guide
Patch instructions, workarounds, and compliance impact
Interactive AI chat
Ask questions about this vulnerability in natural language
Related vulnerabilities
Semantically similar CVEs and attack patterns
REST API & MCP access
Integrate vulnerability data into your workflows